Machine Learning

An Overview of Machine Learning and Additional Resources for Exploration

General Information

Machine learning is the creation of systems capable of learning and improving from "experience" and a subset of artificial intelligence. This means that instead of having to be coding a system to be able to perform a certain task in a certain way, the system learns from examples in a way similar to humans (hence artificial intelligence).

These examples can be images, words, audio, video, or a whole range of other possibilities. To read more, here is a an article on the subject published by MIT.

End-to-End Deep Learning

In this project, CHI@Edge Autonomous Cars with Donkeycar, end-to-end deep learning is utilized. While E2E (end-to-end) deep learning is a complex topic, it can essentially be boiled down to not decomposing. This refers to how machine learning problems are usually decomposed into sub-problems.

However, E2E deep learning allows for a simplification of the learning process by having input passed to a neural network and receive an output, with relevant details abstracted by the network. For more technical details and discussion about this topic, a question called What does end-to-end training mean was posted on the AI Stack Exchange.